Detection of change in posture in video

• US 20060291694A1
• Filed: 06/24/2005
• Published: 12/28/2006
• Est. Priority Date: 06/24/2005
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: ObjectVideo Incorporated (Alarm.com Holdings, Inc.)
• Inventors: Chosak, Andrew J., Haering, Niels, Zhang, Zhong, Venetianer, Peter L., Lipton, Alan J., Yin, Weihong
• Granted Patent: US 7,613,324 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

Input video data is processed to detect a change in a posture of a person shown in the video data. The change of posture may be the result of an event, for example, the person falling or getting up. The input video data may include a plurality of frames. Objects in the frames are tracked and then classified, for example, as human and non-human targets. At least one of the position or location of a human target in the frames is identified. Changes in the location or position of the human target between the frames is determined. When the change in at least of the position or location exceeds a predetermined threshold, a falling down event or a getting up event is detected. The changes in the position or location of the human target can be determined based on a number of different factors.

Claims

1. A method, comprising:

receiving input video data;

processing the video data to detect a change in a posture of a human target in the input video data.

2. The method of claim 1, wherein the change in the posture is detected based on at least one of a height or an aspect ratio of the human target.

3. The method of claim 2, wherein the change in the posture is detected based on at least a location of a top and a bottom of the human target.

4. The method of claim 2, wherein the change in the posture is detected based on at least a trajectory of the human target.

5. The method of claim 1, further comprising tracking a head of the human target.

6. The method of claim 5, wherein the change in the posture is detected based on at least a location of the head.

7. A method, comprising:

receiving input video data;

detecting a target in the video data;

tracking the target;

identifying a target as a human; and

detecting a change in a posture of the human target in the video data.

8. The method of claim 7, wherein the detecting the change step comprises detecting the change in posture when a change in at least one of a height or aspect ratio of the human target exceeds a predetermined threshold.

9. The method of claim 8, wherein the detecting step comprises:

determining the height or the aspect ratio of the target in a first frame of the video data;

determining the height or aspect ratio of the target in a second frame of the video data;

calculating a difference between the height or aspect ratio of the target in the first and second frames; and

detecting the change in the posture when either difference exceeds a predetermined threshold.

10. The method of claim 9, further comprising:

determining an elapsed time between the first and second frames; and

detecting the change in the posture when the elapsed time is below a predetermined threshold.

11. The method of claim 10, further comprising:

determining a second change in the posture has occurred based on a height or aspect ratio of the human target;

determining a length of time between the change in posture and the second change in posture; and

detecting the change in the posture when the elapsed time is below a predetermined threshold.

12. The method of claim 9, further comprising:

determining the height and aspect ratio of the target in a first frame and a third frame of the video data;

determining the length of time between the first and third frames; and

detecting the change in posture when the time is greater than a predetermined threshold.

13. The method of claim 9, further comprising:

tracking a top and bottom of the target; and

detecting the change in the posture based at least in part on the location of the top and bottom of the target.

14. The method of claim 9, wherein the change in the posture is detected when the top of the target moves but the bottom remains in substantially the same location.

15. The method of claim 8, further comprising:

measuring a height of the target; and

detecting the change in posture based on a change in the height of the target.

16. The method of claim 8, further comprising tracking a head of the human target.

17. The method of claim 16, wherein the change in the posture is detected based on at least a location of the head.

18. The method of claim 8, further comprising:

determining a location and position of body parts of the human target; and

detecting the change in posture based on the location and position of the body parts.

19. The method of claim 18, further comprising:

tracking the position and movement of major body parts during a training sequence; and

detecting the change in posture based at least in part on a comparison of the position and movement of the major body parts in the training sequence.

20. A method, comprising:

receiving input video data of a place including a plurality of frames;

tracking objects in the frames;

classifying objects in the frames as human and non-human targets;

identifying at least one of a position or location of a human target in the frames;

determining changes in the location and position of the human target between frames; and

detecting a falling event or a getting up event when the change in at least one of the position or location exceeds a predetermined threshold.

21. The method of claim 20, wherein the identifying step comprises measuring at least one of a height or aspect ratio of the human target, wherein the detecting step comprises calculating a difference in at least one of the height or aspect ratio between frames;

and

determining the change in position or location based on the difference in at least one of the aspect ratio and height.

22. The method of claim 21, further comprising:

determining a trajectory of the human target;

predicting at least one of a height and position of the human target at a point in time;

comparing at least one of the predicted height or position to the actual height or position; and

detecting the falling event or the getting up event based on at least a difference between the predicted and actual height or position.

23. The method of claim 22, further comprising utilizing calibration information to predict the height or position of the human target.

24. The method of claim 20, wherein the determining step comprises tracking a top and bottom of the target;

and

detecting the falling event or getting up event based at least in part on movement of the top and bottom of the target.

25. The method of claim 24, wherein the falling event is detected when the top of the target moves but the bottom remains in substantially the same location.

26. The method of claim 20, wherein the determining step comprises:

determining a height of the target; and

detecting the falling event or getting up event based at least in part on a change in the height of the target.

27. The method of claim 20, further comprising tracking a head of the human target.

28. The method of claim 27, further comprising detecting the falling event or getting up event based at least in part on a location of the head.

29. The method of claim 20, further comprising:

measuring at least one of a speed or duration of the change is aspect ratio or height; and

detecting the falling event or getting up event based at least in part on the speed or duration of the change.

30. The method of claim 20, wherein the place is one of a hospital, store, parking lot, mall, or assisted living community.

31. The method of claim 20, further comprising sending an alert regarding the occurrence of the falling down or getting up event.

32. The method of claim 31, wherein the alert is provided to at least one of hospital staff, security personnel, emergency response personnel, law enforcement.

33. A computer-readable medium containing instructions that when executed by a computer system cause said computer system to implement the method according to claim.

34. A video processing system comprising:

the computer-readable medium according to claim 33;

and

a computer coupled to said computer-readable medium to execute the instructions contained on said computer-readable medium.

35. A method of detecting a person falling or getting up, comprising:

receiving video data of a place from a video camera;

processing the video data to track a persons movements in the place;

determining if the person falls or gets up based on the processing of the video data;

sending an signal indicating the person has fallen or gotten up to an output device when it is determined that the person falls or gets up;

36. The method of claim 35, wherein the place is one of a mall, store, parking lot, assisted living community, hospital, home, or law enforcement environment.